drm/amdkfd: add RAS poison consumption handling for UTCL2 (v2)

Do RAS page retirement and use gpu reset as fallback in UTCL2 fault
handler.

v2: replace vm fault event with posion consumed event in UTCL2
poison consumption.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 7db2421a334039b8f54b9b89b378db44aade6686..56902b5bb7b687a4a09527830c57299b156f42ce 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -308,6 +308,12 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
                struct kfd_vm_fault_info info = {0};
                uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry);
 
+               if (client_id == SOC15_IH_CLIENTID_UTCL2 &&
+                   amdgpu_amdkfd_ras_query_utcl2_poison_status(dev->adev)) {
+                       event_interrupt_poison_consumption(dev, pasid, client_id);
+                       return;
+               }
+
                info.vmid = vmid;
                info.mc_id = client_id;
                info.page_addr = ih_ring_entry[4] |